GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
bergetai
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
bergetai
Model Tree
Cloudflare/clef-flash
Input Modalities
Output Modalities
Supported Functionality
| Test | What it measures | Base | bev |
|---|---|---|---|
| Risk (16,902 questions) | credentials and destructive content in ops text | 93.5% | 97.0% |
| Evasion holdout (90) | evasion attempts never seen in training | 65.6% | 93.3% |
| Red team (34) | adversarial commands | 53% | 74% |
| Jev bench (1,200) | general Jev questions, outside our domain | 80.6% | 82.8% |
The test splits come from the same corpora as training — they measure fit to this kind of traffic, not yours. The evasion and red-team sets are small (90 and 34 cases). Adversarial commands sit at 74%, which is why the gate is one layer among several.
The model keeps CLEF-Flash's joint schema architecture: a single
forward pass answers a map of typed questions (noul/choice/score) over a
shared state. Loading needs the serving stack
(joint_schema_model.py), not AutoModelForCausalLM:
peft (adapter_config.json targets 7
backbone modules)joint_head.safetensorsThe full serving stack is embedded in
Berget AI's System One API; the plugin talks
to it over the Jev POST /v1/systemone contract.
Apache-2.0, matching the base model.